JP7291744B2 - Cruise control method, apparatus, device, vehicle, medium, and program - Google Patents

Description

TECHNICAL FIELD The present invention relates to automatic driving technology, particularly to the field of automatic control technology, and specifically to cruise control methods, apparatuses, devices, vehicles, media, and programs.

With the development of artificial intelligence technology, artificial intelligence has attracted widespread attention in the field of autonomous driving, gradually changing people's driving habits and how they go out.

During automated driving, usually a fixed driving policy is preset in advance to realize cruise control of the driving equipment. However, the above technical solutions are difficult to adapt to different driving users, and the driving experience of the driving users is degraded.

The present invention provides a cruise control method, apparatus, device, vehicle and medium that better match the driving user.

In one aspect of the present invention, a cruise control method is provided, comprising:
obtaining a driving habit weight of at least one candidate driving policy associated with a target driving environment, the driving habit weight being determined based on driving history data of a driving user's past driving device;
selecting a target driving policy from the at least one candidate driving policy based on the driving habit weight;
performing cruise control on the driving user's target driving device based on the target driving policy.

In another aspect of the invention, a cruise control device is provided, comprising:
A driving habit weight of at least one candidate driving policy associated with a target driving environment, the driving habit weight being configured to obtain the driving habit weight determined based on driving history data of a driving user's past driving device. a weight acquisition module;
a target driving policy selection module configured to select a target driving policy from the at least one candidate driving policy based on the driving habit weight;
a cruise control module configured to perform cruise control on the driving user's target driving device based on the target driving policy.

In another aspect of the invention, an electronic device is provided, comprising:
at least one processor;
a memory communicatively coupled to the at least one processor;
Instructions executable by the at least one processor are stored in the memory, and the instructions are provided to the at least one processor in embodiments of the invention when executed by the at least one processor. Execute any cruise control method.

In another aspect of the invention, a vehicle is provided, wherein any electronic device provided in an embodiment of the invention is installed in said vehicle.

Another aspect of the invention provides a non-transitory computer-readable storage medium storing computer instructions, said computer instructions instructing said computer to perform any of the cruise control methods provided in the embodiments of the invention. to run.

According to the present invention, it is possible to improve the adaptability between the cruise control process of the driving user's target driving device and the driving user.

It should be noted that the descriptions herein are not intended to limit the scope of the invention, nor to the key or emphasized features of the embodiments of the invention. Other features of the invention will become easier to understand from the following description of the specification.

4 is a flow chart of a cruise control method according to an embodiment of the present invention; 4 is a flow chart of a driving habit weight determination method in an embodiment of the present invention; 4 is a flow chart of a cruise control method according to an embodiment of the present invention; 4 is a flow chart of a cruise control method according to an embodiment of the present invention; 1 is a structural diagram of a cruise control device according to an embodiment of the present invention; FIG. 1 is a block diagram of an electronic device for implementing a cruise control method according to an embodiment of the invention; FIG.

The above drawings are for better understanding of the invention and are not intended to limit the invention.

DETAILED DESCRIPTION OF THE INVENTION Illustrative embodiments of the invention will now be described with reference to the accompanying drawings, wherein various details of the embodiments of the invention are included for ease of understanding and are merely exemplary. should be regarded as a thing. Accordingly, those skilled in the art should appreciate that various changes and modifications can be made to the described embodiments of the invention without departing from the scope and spirit of the invention. Similarly, in the following description, descriptions of well-known functions and constructions are omitted for clarity and brevity.

Each cruise control method and cruise control device provided in the embodiments of the present invention is applied to the situation of performing cruise control for a driving device with automatic driving or non-automatic driving function. The cruise control method provided in the embodiments of the present invention may be performed by a cruise control device, which is implemented by software and/or hardware and specifically installed in an electronic device. When the electronic device is installed in a driving device, the driving device can be, for example, a vehicle or a steamship. Correspondingly, the electronic device may be an onboard device, a shipboard device, or the like.

FIG. 1 is a flow chart of a cruise control method according to an embodiment of the present invention, which includes the following steps.

In S101, obtain the driving habit weight of at least one candidate driving policy related to the target driving environment, which is determined based on the driving history data of the driving user's past driving device.

The driving environment is used to represent the external environment in which the driving device is placed during driving, and is obtained by data processing based on the data collected by the sensing module and/or positioning based on a high-definition map. is determined by The sensing module may include at least one of sensors such as laser radars, millimeter wave radars, cameras, global positioning systems, inertial measurement units, and the like. Exemplarily, the target driving environment can be represented by a driving environment model constructed from driving environment data. Different driving environments correspond to different driving environment models. Optionally, the driving environment data may include the speed of the driving device itself, the speed of the driving device of the following vehicle, the distance from the driving device of the following vehicle, the type of driving device of the following vehicle, and relative to the driving restraint line. It may include at least one of information such as location. For example, when the driving device is a vehicle, the restricted travel lines may be lanes, guardrails, or the like.

The driving policy is used to represent the control policy that the driving device adheres to while driving. In one embodiment, the driving policy may include at least one of policies such as go straight, turn right, turn left, change right lane, change left lane, overtake left, overtake right, and stop.

Since the driving environments of the driving devices are different, the candidate driving policies are correspondingly the same or not the same. For example, in a driving environment in which the driving device follows the preceding driving device in a multi-passage direct environment, the driving policy is one of the policies for executing right lane change, left lane change, overtaking on the left side, overtaking on the right side, and stopping progress. and may not include right-handed and left-handed policies. In addition, since the driving environments of the driving devices are different, the driving habit weights of the candidate driving policies may or may not be the same. For example, in a driving environment in which the driving device follows the leading driving device in a multi-passage direct environment, the driving habit weight corresponding to the clockwise driving policy and the counterclockwise driving policy may be 0, whereas, At least one of the driving habit weights corresponding to the clockwise driving policy and the counterclockwise driving policy is not 0 in the driving environment in which the driving device in the T-shaped passage area follows the preceding driving device.

In this embodiment, the driving habit weight is used to represent the driving habit status of the driving user in the target driving environment. The driving history data is data generated by the past driving device when the driving user drives the driving device manually or semi-automatically.

Optionally, the driving habit weight of each candidate driving policy associated with the target driving environment can be stored locally on the electronic device, on other storage devices associated with the electronic device, or on the cloud side; When , data retrieval can be performed and searched from the electronic device local, other storage devices associated with the electronic device, or from the cloud side.

In one embodiment, one operating device may be shared by multiple operating users. Since the driving habits of different driving users have differences, the driving habit parameters of each candidate driving policy must also have differences in different driving environments of different driving users. In order to cope with situations where one driving device is adapted to multiple driving users and to improve the degree of matching of driving users when performing cruise control of the target driving device in the relevant scene, at least one related to the target driving environment is provided. Obtaining the driving habit weight of the candidate driving policy may be obtaining the driving habit weight of at least one candidate driving policy associated with the driving user in the target driving environment.

What should be done is to differentiate the driving habit weights based on the driving user and the driving environment, so that the acquisition demands of the driving habit weights of different driving users and in different driving environments can be adapted, and finally It may be understood as laying the groundwork for better matching of the cruise control process and the driving user.

At S102, a target driving policy is selected from at least one candidate driving policy based on the driving habit weight.

In one optional embodiment, selecting the target driving policy from the at least one candidate driving policy based on the driving habit weight includes selecting from the at least one candidate driving policy one having a relatively high driving habit weight. Selecting the candidate driving policy as the target driving policy and thereby providing data support to the cruise control of the driving user's target driving device.

In addition, since some bad driving habits may exist in the driving habits of the driving user, the driving habit weight determined based on the driving history data of the driving user's past driving device may cause a case where bad driving behavior is recognized. and thereby threaten the driving safety of the driving user. To avoid the above situation, a reference decision weight can be introduced to modify the driving habit weight.

In another optional embodiment, selecting the target driving policy from the at least one candidate driving policy based on the driving habit weights includes: and selecting a target driving policy from the at least one candidate driving policy based on the adjusted driving habit weights.

A reference decision weight can be understood to be a weight that is determined for each candidate driving policy, taking into account factors such as safety in the target driving environment. Candidate driving policies that are safer in the target driving environment have a higher corresponding reference decision-making weight, and candidate driving policies that are less safe in the target driving environment have a corresponding reference decision-making weight.

It should be noted that the reference decision weight for each candidate driving policy can be set by an engineer as needed or according to empirical values, or determined by a large number of repeated tests, or by a conventional weight determination mechanism. may be determined, and the embodiment of the present invention does not limit the method of determining the reference decision weight of each candidate driving policy.

Illustratively, calculating driving habit weights based on the reference decision weights of the candidate driving policies to obtain adjusted driving habit weights, and determining from at least one candidate driving policy that the adjusted driving habit weights are relatively high. A high candidate driving policy may be selected as the target driving policy.

Alternatively, the operations performed on the driving habit weights based on the reference decision weights of the candidate driving policies can be implemented in manners such as additive or multiplicative operations.

In S103, cruise control is performed on the target driving device of the driving user based on the target driving policy.

The target driving device can be understood to be the target driving device that the driving user uses in the target driving environment.

Alternatively, the target operating device may be the same as the previous operating device. That is, when determining the target driving policy, the target driving policy is determined based on the driving habit weight determined by the driving history data of the target driving device of the driving user, and cruise control is performed on the target driving device. Note that when the number of past operating devices is at least one, the target operating device may be one of the past operating devices.

Or, alternatively, the target operating device may be different from the previous operating device. By way of example, the driving habit weight determined by the driving history data when the driving user A was driving the vehicle a is applied to the cruise control scene in which the driving user A rides the vehicle b. Implement cruise control for vehicle b.

As an example, the driving route is re-planned based on the target driving policy, and the target driving device is subjected to cruise control such as going straight, turning a curve, or stopping progress based on the planned driving route. Here, the curving includes at least one of counterclockwise, clockwise, left lane change, right lane change, overtaking on the left, overtaking on the right, and the like.

Optionally, based on the target driving policy, when the target driving device of the driving user is subjected to cruise control, the driving user can obtain the driving situation of the target driving device in a timely manner. The target driving policy may also be fed back to the driving user before or at the time cruise control is applied to the vehicle. In order to avoid a bad user experience for the driving user due to frequent feedback of the target driving policy to the driving user, the target driving policy is selectively compared with the original driving policy currently in use to determine the target driving policy. If the driving policy is different from the original driving policy, feedback the target driving policy to the driving user.

In an embodiment of the present invention, a driving habit weight of at least one candidate driving policy related to a target driving environment is obtained, the driving habit weight is determined based on the driving history data of the driving user's past driving devices, and the driving habit A target driving policy is selected from at least one candidate driving policy based on the weight, and cruise control is performed on the target driving device of the driving user based on the target driving policy. In an embodiment of the present invention, the target driving policy is determined based on the driving habit weight determined by the driving history data of the driving user's past driving device, and the determined target driving policy is the target driving environment of the driving user. to adapt to the driving habits of the driving user, thereby improving the driving user's fitness with the driving user when performing cruise control on the target driving device, and the driving user's experience when riding the target driving device improve.

Based on the above technical solutions, the driving habit weight determination operation may be performed in advance, and the driving habit weight may be determined before using the driving habit weight during cruise control.

Embodiments of the present invention further provide a driving habit weight determination method, which is used during cruise control to determine the driving habit weight of a candidate driving policy associated with a target driving environment.

Illustratively, the driving habit weight may be determined based on the driving history data of the driving user's past driving devices.

In one embodiment, the travel history data may include at least one of the following: passage number statistical data of the number of past driving device trips on each passage (different passages have different passage attributes); Aisle time length statistical data of the running time length of the driving device, user feedback time length statistical data when the past driving device changed the policy, policy number statistical data of the past driving number of the driving device in each candidate driving policy, and It may include policy length of time statistical data of the length of time traveled by past driving devices in each candidate driving policy. Here, the passage includes, but is not limited to, a route for steamship travel, a roadway for vehicle travel, or the like.

Illustratively, the path number statistical data of the number of past driving device trips on each path is used to represent the driving user's preferences for paths with different path attributes in terms of the number of times of driving. The path attributes may include at least one of path width, permissible traffic speed, path position in parallel paths, and the like. To give an example, when user A drives a past vehicle on three parallel roads, if it is assumed that he always drives on the low-speed road, the statistical data of the number of times on the low-speed road is high, and the number of times on the high-speed road is high. Low count statistics.

Illustratively, the path length statistical data of the length of time traveled by past driving devices on each path is used to represent the driving user's preference for paths with different path attributes in the dimension of length of driving time. To give an example, when user A drives a past vehicle on three parallel lanes, if it always runs on a low-speed road, the time length statistical data on the low-speed road is high, and on the high-speed road Low duration statistics.

Illustratively, the user feedback duration statistical data when the past driving device made a policy change is used to represent the driving user's preference for each candidate driving policy in the dimension of user decision making. For example, while the user A drives the past vehicle, the past vehicle determines the target driving policy and provides feedback to the user A to decide whether to implement it, and the feedback time length of the user A is long. If the feedback time length of user A is short, it indicates that user A has a high degree of liking for the target driving policy.

Illustratively, the policy count statistical data of the number of past driving device trips in each candidate driving policy is used to represent the driving user's preference for the candidate driving policy in terms of the number of policy executions. To give an example, if the cumulative number of times that a candidate driving policy with a certain past vehicle is used is large when user A is driving a past vehicle, user A has a high degree of liking for that candidate driving policy. If the cumulative number of times that a given candidate driving policy has been used by a past vehicle is small, it means that the degree of user A's preference for the candidate driving policy is low.

Illustratively, the policy duration statistics of past driving device duration in each candidate driving policy are used to represent the driving user’s preference for the candidate driving policy in terms of policy execution duration. To give an example, when the user A is driving a past vehicle and the cumulative length of time during which the past vehicle uses a certain candidate driving policy is long, the user A's degree of preference for the candidate driving policy is If the cumulative time length of past vehicles using a candidate driving policy is short, it means that user A's preference for the candidate driving policy is low.

The drive history data exemplified above can enrich the driving habit weight determination mechanism. Based on the above technical solution, in one alternative embodiment of the present invention, FIG. 2 illustrates a driving habit weight determination method, which includes the following steps.

At S201, a path weight is determined based on the path number statistical data and/or the path time length statistical data.

Exemplarily, a first path selection frequency corresponding to paths with different path attributes is determined based on the path number statistical data, and a second path selection frequency corresponding to paths with different path attributes is determined based on the path time length statistical data. and determine a path weight based on the first path selection frequency and/or the second path selection frequency.

Alternatively, the first path selection frequency may be directly used as the path weight and the second path selection frequency may be used as the path weight, or the weighted sum of the first path selection frequency and the second path selection frequency may be used as the path weight. can. Here, the weights of the first path selection frequency and the second path selection frequency can be determined by the engineer as required or according to empirical values. It should be noted that the above method is merely an example of how to determine the path weight, and other methods may be used to determine the path weight, and the embodiments of the present invention are not limited thereto.

At S202, user feedback weights are determined based on the user feedback duration statistics.

Illustratively, the user feedback weight of each candidate driving policy can be determined based on a preset feedback weight determination function, user feedback duration statistical data. Here, the preset feedback weight determination function is a decreasing function of the user feedback duration statistical data, that is, the user feedback weight decreases as the user's feedback duration increases.

Exemplarily, determining the ratio of the feedback duration corresponding to each candidate driving policy based on the user feedback duration statistical data, and determining the user feedback weight of each candidate driving policy based on the ratio of the feedback duration. , where the user feedback weight decreases with increasing ratio of the feedback duration.

In addition, in the above method, the user feedback weight determination method is shown as an example, and the user feedback weight may be determined by other methods, and the embodiments of the present invention are not limited thereto.

At S203, the policy weight is determined based on the policy count statistical data and/or the policy time length statistical data.

Exemplarily, the first policy selection frequency corresponding to each candidate driving policy is determined based on the policy frequency statistical data, and the second policy selection frequency corresponding to each candidate driving policy is determined based on the policy duration statistical data. and determining a policy weight based on the first policy selection frequency and/or the second policy selection frequency.

Alternatively, the first policy selection frequency can be directly used as the policy weight, the second policy selection frequency can be used as the policy weight, or the weighted sum of the first policy selection frequency and the second policy selection frequency can be used as the policy weight. . Here, the weights of the first policy selection frequency and the second policy selection frequency can be determined by engineers according to needs or empirical values. It should be noted that the above method is merely an exemplary policy weight determination method, and other methods may be used to determine the policy weight, and the embodiments of the present invention are not limited thereto.

At S204, driving habit weights are determined based on at least one of path weights, user feedback weights, and policy weights.

Illustratively, based on the current driving aisle of the target driving device in the target driving environment, using the target driving aisle corresponding to each candidate driving policy, determine the aisle weight of each candidate driving policy; A driving habit weight for each candidate driving policy is determined based on at least one of the path weight, the user feedback weight, and the policy weight.

Optionally, at least one of the path weight, user feedback weight, and policy weight of each candidate driving policy is directly made the driving habit weight.

Alternatively, optionally, processing is performed on at least two of the path weight, the user feedback weight, and the policy weight of each candidate driving policy, and the processing result is the driving habit weight of each candidate driving policy. Here, the numerical value of the driving habit weight increases with the increase of the route weight, user feedback weight, and policy weight of the candidate driving policy.

Illustratively, processing on at least two of the path weight, the user feedback weight, and the policy weight of each candidate driving policy comprises performing at least one of a weighting operation, a multiplication operation, and an exponentiation operation. It can be realized by

In an embodiment of the present invention, at least one of pass count statistical data, pass duration statistical data, user feedback duration statistical data, policy count statistical data, and policy length statistical data is taken to determine driving habit weights. , thereby enriching the driving habit weight determination mechanism, the finally determined driving habit weight can represent the driving habits of the driving user in different dimensions and different levels, so that the driving habit parameters Lay a foundation to improve the degree of matching between the target driving policy determined based on and the driving user.

Based on the above technical solutions, when the target driving device is the past driving device, two different driving modes, the learning mode and the normal mode, are applied to the target driving device in order to determine the driving habit weight of the driving user in the target driving device. Models can be pre-installed. When the target driving device is in the normal mode, the target driving device enters an automatic driving cruise control state, and when the target driving device is in the learning mode, the target driving device enters a learning state of the driving user's driving habits, thereby: Lays the groundwork for cruise control for subsequent target driving devices.

In one embodiment, when the current driving mode is the learning mode, the operation of "executing cruise control on the target driving device of the driving user based on the driving policy" is replaced by "feeding back the target driving policy to the driving user." and receive a feedback command from the driving user, perform cruise control on the driving user's target driving device based on the feedback command, and update the driving habit weight based on the newly generated driving data. refinement, thereby improving the cruise control mechanism for the target driving device.

Referring to FIG. 3, another cruise control method is shown and includes the following steps.

At S301, obtaining the driving habit weight of at least one candidate driving policy related to the target driving environment, the driving habit weight is determined based on the driving history data of the driving user's past driving devices.

At S302, select a target driving policy from at least one candidate driving policy based on the driving habit weight.

In S303, if the current driving mode is the learning mode, feedback the target driving policy to the driving user and receive the driving user's feedback instruction.

If the current driving mode is the learning mode, feedback the target driving policy to the driving user, and the driving user responds to the target driving policy and generates a feedback instruction.

Here, the feedback command may be an acceptance command and is used to indicate that the target driving policy is accepted, and the feedback command may be a rejection command that indicates that the target driving policy is not accepted. used to represent In order to avoid erroneous operation by the driving user, feedback of the target driving policy to the driving user may be implemented by adopting at least one of methods such as voice notification, text display, and video display. After receiving the driving user's feedback instruction, at least one of methods such as voice notification, text display, and video display may be employed to display the driving user's feedback instruction.

At S304, update the driving habit weight based on the newly generated driving data to perform cruise control on the driving user's target driving device according to the feedback command.

Illustratively, performing cruise control on the driving user's target driving device based on the feedback command may include performing cruise control on the driving user's target driving device based on the target driving policy if the feedback command is an acceptance command. to perform cruise control,
If the feedback instruction is a refusal instruction, it may be prohibiting the driving user's target driving device from performing cruise control based on the target driving policy.

Optionally, disabling cruise control on the driving user's target driving device based on the target driving policy means performing cruise control on the driving user's target driving device based on the original driving policy. and the original driving policy may be the driving policy adopted before determining the target driving policy. Alternatively, selectively prohibiting the target driving device of the driving user from performing cruise control based on the target driving policy means adopting the default driving policy or the driving user-specified driving policy and It may be performing cruise control on the user's target driving device.

For example, when the target driving policy is to overtake on the right side while the target vehicle is traveling straight, if the driving user's feedback command is an acceptance command, the target vehicle is controlled to overtake on the right side. do. If the driving user's feedback order is a rejection order, keep the original direct policy. Or, get the default policy and control the target vehicle to overtake and proceed on the left if the default policy is overtaking on the left. Alternatively, the driving policy specified by the driving user is acquired, and if the specified driving policy is overtaking on the left side, the target vehicle is controlled to overtake on the left side.

The above technical solution adopts different selectable methods according to the acceptance or rejection of the command to perform cruise control for the target driving device and improve the cruise control mechanism for the target driving device. It should be understood that it is possible.

Exemplarily, the driving habit weight is updated based on the newly generated driving data, and the newly generated driving data is directly used as the driving history data of the target driving device to determine or update the driving habit weight again. do.

An embodiment of the present invention introduces a learning mode into the target driving device, and in the learning mode, performs cruise control on the target driving device based on a feedback command of the driving user's target driving policy, and controls the target driving device. While driving, it realizes online learning of the driving user's driving habits and lays the foundation for subsequent cruise control for the target driving device or cruise control for other driving devices.

Based on the above technical solutions, the embodiments of the present invention further provide preferred embodiments for the case of performing cruise control on the target vehicle running on the roadway.

Shown in FIG. 4 is another cruise control method, applied to the target vehicle, which includes the following steps.

S410 is the driving habit weight determination stage, and S420 is the cruise control stage.

Illustratively, the driving habit weight determination phase includes the following steps.

At S411, the target driving environment of the target vehicle is determined.

In S412, when the driving user drives the target vehicle in the target driving environment, the roadway weight of each roadway is determined based on the past number of times of driving on roadways with different attributes.

In S413, the roadway weight of the corresponding roadway when the candidate driving policy is used is set as the roadway weight of the candidate driving policy.

Here, the candidate driving policies include at least one of policies for executing clockwise, counterclockwise, right lane change, left lane change, overtaking on the left, overtaking on the right, stopping, and the like.

In S414, the user feedback weight of each candidate driving policy is determined based on the past feedback time length for each candidate driving policy in the driving user's target driving environment.

In S415, the policy weight of each candidate driving policy is determined based on the number of times the driving user used each candidate driving policy in the target driving environment in the past.

At S416, the weighted sum of the roadway weight, the user feedback weight, and the policy weight is determined, and the sum is taken as the driving habit weight.

Illustratively, the cruise control phase includes the following steps.

In S421, the driving habit weight of each candidate driving policy related to the target driving environment of the driving user is obtained.

At S422, the reference decision weight of the candidate driving policy is weighted to the driving habit weight to update the driving habit weight.

At S423, a target driving policy with a high driving habit weight is selected from among the candidate driving policies related to the target driving environment.

In S424, it is determined whether or not the current operation mode is the learning mode, and if so, S425 is executed; otherwise, S426 is executed.

If the current driving mode is the learning mode, the target driving policy is fed back to the driving user, and the driving user decides whether or not to perform cruise control on the target vehicle based on the target driving policy, and the current driving mode is the non-learning mode. In the normal mode, cruise control is directly applied to the target vehicle based on the target driving policy.

In S425, it is determined whether the driving user accepts the target driving policy, if yes, execute S426, otherwise execute S427.

At S426, driving of the target vehicle is controlled based on the target driving policy. Continue executing S428.

At S427, continue to control the driving of the target vehicle based on the original driving policy. Continue executing S428.

In S428, the number of times the driving user has traveled on roads with different attributes in the target driving environment, the past feedback time length for the candidate driving policy, and the number of times the candidate driving policy has been used in the past are updated.

An embodiment of the present invention incorporates driving habit parameters to determine a candidate driving policy, so that the finally determined target driving policy can adapt to the driving habits of the driving user in different driving environments; The vehicle cruise control process can meet the driving user's individual needs.

As an implementation of the method shown in the above figures, the present invention further provides an embodiment of a virtual device implementing the cruise control method. Shown in FIG. 5 is a cruise control device 500 , comprising a driving habit weight acquisition module 501 , a target driving policy selection module 502 and a cruise control module 503 .

A driving habit weight obtaining module 501 is configured to obtain a driving habit weight of at least one candidate driving policy associated with a target driving environment, where the driving habit weight is the driving history data of the driving user's past driving devices. determined based on

The target driving policy selection module 502 is configured to select a target driving policy from the at least one candidate driving policy based on the driving habit weight.

The cruise control module 503 is configured to perform cruise control on the target driving device of the driving user based on the target driving policy.

An embodiment of the present invention obtains the driving habit weight of at least one candidate driving policy related to the target driving environment by a driving habit weight obtaining module, where the driving habit weight is the driving history of the driving user's past driving device a target driving policy selection module based on the driving habit weight; selecting a target driving policy from at least one candidate driving policy based on the driving habit weight; Cruise control is performed for the target operating device. An embodiment of the present invention incorporates a driving habit weight determined based on the driving history data of the driving user's past driving devices to determine a target driving policy, whereby the determined target driving policy is the driving user's It can adapt to the driving habits in the target driving environment, thereby improving the fitness with the driving user when performing cruise control on the target driving device of the driving user, and when the driving user gets on the target driving device. Improve your experience.

Further, the historical driving data includes at least one of:
Statistical data on the number of times the operating device has traveled in each passage (different passages have different passage attributes);
Passage time length statistical data of travel time length of the past operating device in each passage,
User feedback time length statistical data when the past operating device changed the policy,
policy frequency statistical data of the number of times the driving device has traveled in the past in each candidate driving policy; and
policy time length statistical data of the driving time length of past driving devices in each candidate driving policy;

Additionally, the apparatus further comprises a driving habit weight determination module configured to determine a driving habit weight;
Here, the driving habit weight determination module is
a path weight determination unit configured to determine a path weight based on the path number statistical data and/or the path length statistical data;
a user feedback weight determination unit configured to determine a user feedback weight based on the user feedback duration statistics;
a policy weight determination unit configured to determine a policy weight based on the policy times statistical data and/or the policy duration statistical data;
a driving habit weight determination unit configured to determine the driving habit weight based on at least one of the path weight, the user feedback weight, and the policy weight.

Furthermore, the target driving policy selection module 502
a driving habit weight adjustment unit configured to make adjustments to the driving habit weight based on the reference decision weight of the candidate driving policy;
a target driving policy selection unit configured to select a target driving policy from the at least one candidate driving policy based on the adjusted driving habit weights.

Furthermore, if the current driving mode is the learning mode, the cruise control module 503 will:
a feedback receiving unit configured to feed back the target driving policy to the driving user and receive the driving user's feedback instructions;
a cruise control unit configured to update the driving habit weights based on newly generated driving data to cruise control the driving user's target driving device based on the feedback instructions.

Additionally, the cruise control unit
a cruise control acceptance subunit configured to perform cruise control on the target driving device of the driving user based on the target driving policy if the feedback instruction is an acceptance instruction;
a cruise control denial subunit configured to prohibit cruise control on the target driving device of the driving user based on the target driving policy if the feedback command is a denial command.

Furthermore, the driving habit weight acquisition module 501
a driving habit weight obtaining unit configured to obtain the driving habit weight of at least one candidate driving policy associated with the driving user in the target driving environment.

Further, the candidate driving policies include at least one of the following: straight, clockwise, counterclockwise, right lane change, left lane change, overtake left, overtake right, and stop.

The above cruise control device is capable of implementing the cruise control method provided in any embodiment of the present invention, has functional modules corresponding to the cruise control method, and has beneficial effects.

According to embodiments of the invention, the invention further provides an electronic device and a readable storage medium.

Shown in FIG. 6 is a block diagram of an electronic device implementing the cruise control method in an embodiment of the present invention. Electronic devices refer to each type of digital computer, including laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, large computers, and other suitable computers. Electronic devices further refer to each type of mobile device, including, for example, personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components, their connections, and functions described in the invention are exemplary only, and do not limit the implementation of what is described and specified in the invention.

As shown in FIG. 6, the electronic device includes one or more processors 601, memory 602, and interfaces for connecting components, including high speed interfaces and low speed interfaces. Each component is connected by a different bus and can be attached to a common motherboard, or otherwise attached as desired. The processor is capable of executing instructions to be executed by the electronic device, instructions stored in memory, or graphical information stored in an external input/output device (e.g., a display device coupled to the interface) and displayed in a GUI. including instructions for In other embodiments, multiple processors and/or multiple buses and multiple memories may be used together if desired. Similarly, multiple electronic devices can be connected, each providing its own required operation (eg, a group of blade servers as a server array, or multiple processor systems). In FIG. 6, one processor 601 is taken as an example.

Memory 602 is a non-transitory computer-readable storage medium provided for the present invention. Here, instructions for execution by at least one processor are stored in the memory to cause the at least one processor to perform the cruise control method provided in the present invention. Computer instructions are stored in the non-transitory computer-readable storage medium of the present invention, the computer instructions causing the computer to perform the cruise control method provided in the present invention.

The memory 602 may be for storing non-transitory software programs as a non-transitory computer-readable storage medium, the non-transitory computer being able to execute the programs and modules, e.g. , executing program instructions/modules corresponding to the cruise control method in an embodiment of the present invention (eg, the driving habit weight acquisition module 501, the target driving policy selection module 502, and the cruise control module 503 shown in FIG. 5). can. The processor 601 executes the non-transitory software programs, instructions and modules stored in the memory 602 to perform the functions and data processing of the server, i.e. implement the cruise control method in the above method embodiments. do.

The memory 602 includes a program storage area and a data storage area, where in the program storage area an operating system, application programs required for at least one function can be stored, and in the data storage area the electronic device according to the cruise control method. may be stored such as data generated by the use of Memory 602 may also include high speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash device, or other non-transitory solid state memory device. In some embodiments, memory 602 optionally includes memory located remotely from processor 601, and these remote memories can be connected by a network to the electronic device executing the cruise control method. Examples of the above networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The electronic device implementing the cruise control method may further include input device 603 and output device 604 . Processor 601, memory 602, input device 603, and output device 604 may be connected by a bus or in other manners, with the connection by bus being taken as an example in FIG.

The input device 603 can receive input numeric or character information and generate keyboard signal inputs associated with user settings and functional control of electronic devices implementing cruise control methods, such as touch screen, numeric keypad, mouse, Input devices include trackplates, touch tablets, indicators, one or more mouse buttons, trackballs, joysticks, and the like. Output devices 604 may include display devices, lighting aids (eg, LEDs), tactile feedback devices (eg, vibration motors), and the like. Such display devices include, but are not limited to, liquid crystal displays (LCD), light emitting diode (LED) displays, and plasma displays. In some embodiments, the display device may be a touch screen.

Embodiments of the systems and techniques described herein may be implemented in digital electronic circuit systems, integrated circuit systems, dedicated application specific integrated circuits (ASICs), computer hardware, firmware, software, and/or combinations thereof. can be Each of these embodiments may include implementation in one or more computer programs, which are executed and/or implemented in a programmable system including at least one programmable processor. Or, the programmable processor may be a special purpose or general purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device. can transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

These computer programs (also referred to as programs, software, software applications, or code) include programmable processor machine instructions and can be implemented using high-level procedural and/or object-oriented programming languages and/or assembly/machine language. Implement these computer programs. For example, as used herein, the terms "machine-readable medium" and "computer-readable medium" refer to computer program products, devices for providing machine instructions and/or data to a programmable processor. , and/or device (eg, disk, compact disk, memory, programmable logic device (PLD)) that includes a machine-readable medium for receiving machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal for providing machine instructions and/or data to a programmable processor.

The systems and techniques described herein can be implemented in a computer to provide interaction with a user, and the computer may include a display device (e.g., CRT (cathode ray tube)) for displaying information to the user. ) or LCD (liquid crystal display) monitor), and a keyboard and pointing device (e.g., a mouse or trackball) through which a user can provide input to the computer. Other types of devices can be used to provide interaction with a user, e.g., providing feedback to the user in any form of sensory feedback (e.g., visual, auditory, or tactile feedback). There may be, and input may be received from the user in any form (sound, voice, or tactile).

You can use the systems and techniques described herein as a computing system that includes background components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front components (e.g., , a user computer having a GUI or network browser, through which a user can interact with embodiments of the systems and techniques described herein), or such background components; Any combination of middleware components, or front components, can be implemented in the computing system. The components of the system can be connected together via any form or medium of digital data communication (eg, a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. By running on corresponding computers, computer programs have a client-server relationship, thereby creating a client-server relationship. The server may be a cloud server, also called a cloud computing server or cloud host. It is a cloud computing service system host product to solve the difficult management and weak business scalability of traditional physical host and VPS services.

According to the technical solution of the embodiment of the present invention, the driving habit weight determined based on the driving history data of the driving user's past driving device is taken to determine the target driving policy, and the target driving policy determined accordingly. can adapt to the driving habits of the driving user in the target driving environment, thereby improving the fitness with the driving user when performing cruise control on the driving user's target driving device, and allowing the driving user to perform the target driving To improve the experience of riding the device.

Embodiments of the present invention further provide a vehicle, in which the electronic device shown in FIG. 6 is installed, which can be an in-vehicle terminal, a mobile terminal, or the like.

It should be appreciated that steps can be reordered, added or deleted using each type of process described above. As long as the expected result of the technical solution disclosed in the present invention can be achieved, for example, each step described in the present invention can be performed in parallel, in sequence, or randomly. and the invention is not so limited.

The above specific embodiments do not constitute limitations on the protection scope of the present invention. Obviously, those skilled in the art can make modifications, combinations, sub-combinations and substitutions based on design requirements and other factors. Any modification, equivalent replacement, improvement, etc. within the idea and principle of the present invention shall all fall within the protection scope of the present invention.

Claims (16)

A cruise control method performed by a cruise control device, comprising:
Driving habit weights of at least one candidate driving policy associated with a driving user in a target driving environment when the driving device is shared by a plurality of driving users, and driving history data of past driving devices of the driving user. obtaining the driving habit weight determined based on
selecting a target driving policy from the at least one candidate driving policy based on the driving habit weight;
performing cruise control on the driving user's target driving device based on the target driving policy;
selecting a target driving policy from the at least one candidate driving policy based on the driving habit weights;
making an adjustment to the driving habit weight based on a reference decision weight of the candidate driving policy;
selecting the target driving policy from the at least one candidate driving policy based on adjusted driving habit weights;
The reference decision-making weight is a weight determined for each candidate driving policy in consideration of safety factors in the target driving environment. A candidate driving policy that has a higher reference decision-making weight and is less safe in the target driving environment has a lower corresponding reference decision-making weight.
cruise control method. The travel history data includes the following passage number statistical data of the number of times the driving device has traveled on each passage with different passage attributes,
Passage time length statistical data of the travel time length in each of the passages of the past operation device;
User feedback time length statistical data when the past operation device changed the policy,
policy frequency statistical data of the number of times of driving in each of the candidate driving policies of the past driving device; and
policy time length statistical data of the driving time length in each of the candidate driving policies of the past driving device;
including at least one of
The user feedback time length is the time required for the user to decide whether to execute the target driving policy determined by the past vehicle while driving the past vehicle .
The cruise control method according to claim 1. determining the driving habit weights based on at least one of path weights, user feedback weights, and policy weights;
the path weight is determined based on the path number statistical data and/or the path length statistical data;
the user feedback weight is determined based on the user feedback duration statistics;
the policy weight is determined based on the policy count statistical data and/or the policy duration statistical data;
The cruise control method according to claim 2. When the current driving mode is the learning mode, performing cruise control on the target driving device of the driving user based on the target driving policy includes:
feeding back the target driving policy to the driving user and receiving the driving user's feedback instructions;
performing cruise control on the driving user's target driving device based on the feedback instructions and updating the driving habit weights based on newly generated driving data;
The cruise control method according to claim 1. performing cruise control on the driving user's target driving device based on the feedback command;
performing cruise control on a target driving device of the driving user based on the target driving policy if the feedback command is an acceptance command;
disabling cruise control for the driving user's target driving device based on the target driving policy if the feedback command is a rejection command;
The cruise control method according to claim 4 . the candidate driving policy includes at least one of straight, clockwise, counterclockwise, right lane change, left lane change, left overtaking, right overtaking, and stop progressing;
The cruise control method according to any one of claims 1-5 . A cruise control device,
Driving habit weights of at least one candidate driving policy associated with a driving user in a target driving environment when the driving device is shared by a plurality of driving users, and driving history data of past driving devices of the driving user. a driving habit weight acquisition module configured to obtain driving habit weights determined based on;
a target driving policy selection module configured to select a target driving policy from the at least one candidate driving policy based on the driving habit weight;
a cruise control module configured to perform cruise control on the driving user's target driving device based on the target driving policy ;
The target driving policy selection module includes:
a driving habit weight adjustment unit configured to make adjustments to the driving habit weight based on a reference decision weight of the candidate driving policy;
a target driving policy selection unit configured to select the target driving policy from the at least one candidate driving policy based on adjusted driving habit weights;
The reference decision-making weight is a weight determined for each candidate driving policy in consideration of safety factors in the target driving environment. A candidate driving policy that has a higher reference decision-making weight and is less safe in the target driving environment has a lower corresponding reference decision-making weight.
cruise control device. The travel history data includes the following passage number statistical data of the number of times the driving device has traveled on each passage with different passage attributes,
Passage time length statistical data of the travel time length in each of the passages of the past operation device;
User feedback time length statistical data when the past operation device changed the policy,
policy frequency statistical data of the number of times of driving in each of the candidate driving policies of the past driving device; and
policy time length statistical data of the driving time length in each of the candidate driving policies of the past driving device;
including at least one of
The user feedback time length is the time required for the user to decide whether to execute the target driving policy determined by the past vehicle while driving the past vehicle .
The cruise control device according to claim 7 . further comprising a driving habit weight determination module configured to determine the driving habit weight based on at least one of path weight, user feedback weight, and policy weight;
The driving habit weight determination module includes:
a path weight determination unit configured to determine the path weight based on the path number statistical data and/or the path duration statistical data;
a user feedback weight determination unit configured to determine the user feedback weight based on the user feedback duration statistics;
a policy weight determination unit configured to determine the policy weight based on the policy times statistical data and/or the policy duration statistical data;
comprising
The cruise control device according to claim 8 . If the current driving mode is learning mode, the cruise control module:
a feedback receiving unit configured to feed back the target driving policy to the driving user and receive feedback instructions of the driving user;
a cruise control unit configured to perform cruise control on the driving user's target driving device based on the feedback instructions and to update the driving habit weights based on newly generated driving data. prepare
The cruise control device according to claim 7 . The cruise control unit is
a cruise control acceptance subunit configured to perform cruise control on the driving user's target driving device based on the target driving policy when the feedback command is an acceptance command;
a cruise control rejection subunit configured to prohibit cruise control on the driving user's target driving device based on the target driving policy if the feedback command is a rejection command. ,
A cruise control device according to claim 10 . the candidate driving policy includes at least one of straight, clockwise, counterclockwise, right lane change, left lane change, left overtaking, right overtaking, and stop progressing;
A cruise control device according to any one of claims 7 to 11 . an electronic device,
comprising at least one processor and memory communicatively coupled to the at least one processor;
Instructions executable by the at least one processor are stored in the memory, and when the instructions are executed by the at least one processor, the at least one processor performs any of claims 1 to 6 . Execute the cruise control method according to or
electronic device. A vehicle in which the electronic device according to claim 13 is installed. A non-transitory computer readable storage medium for storing instructions for causing a computer to perform the cruise control method of any one of claims 1-6 . A program characterized by realizing the cruise control method according to any one of claims 1 to 6 when executed by a processor in a computer.

Images